{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:43:06Z","timestamp":1784212986500,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101400"],"award-info":[{"award-number":["2018AAA0101400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803085"],"award-info":[{"award-number":["61803085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921004"],"award-info":[{"award-number":["61921004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1713209"],"award-info":[{"award-number":["U1713209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province of China","doi-asserted-by":"publisher","award":["BK20202006"],"award-info":[{"award-number":["BK20202006"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/tsmc.2021.3050960","type":"journal-article","created":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T21:04:14Z","timestamp":1613163854000},"page":"2757-2769","source":"Crossref","is-referenced-by-count":81,"title":["Asynchronous Multithreading Reinforcement-Learning-Based Path Planning and Tracking for Unmanned Underwater Vehicle"],"prefix":"10.1109","volume":"52","author":[{"given":"Zichen","family":"He","sequence":"first","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/app9173456"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/UT.2019.8734349"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2541020"},{"key":"ref30","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885374"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2884797"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11804-019-00089-3"},{"key":"ref34","first-page":"85","article-title":"Reinforcement learning neural network to the problem of autonomous mobile robot obstacle avoidance","volume":"1","author":"huang","year":"2005","journal-title":"Proc IEEE Int Conf Mach Learn Cybern"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2227719"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2785794"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2016.2537984"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2500027"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2645699"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)37809-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/acs.2550"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2009.10.004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2005.02.012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2564930"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2465352"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2016.2628803"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5755\/j01.itc.48.2.21390"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2345734"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s00773-015-0355-9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487125"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2465174"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931199"},{"key":"ref40","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s12541-019-00224-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087247"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2005.1626816"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER46603.2019.9066639"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2017.2700633"},{"key":"ref16","first-page":"262","article-title":"Anytime dynamic A*: An anytime, replanning algorithm","volume":"5","author":"likhachev","year":"2005","journal-title":"Proc ICAPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSE.2019.8867535"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.10.025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2018.2792278"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2014.2381359"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12127-3_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14257\/ijsh.2014.8.3.07"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2991\/meita-15.2015.57"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-013-0750-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2019.8816410"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref9","article-title":"An overview of the class of rapidly-exploring random trees","author":"guevara","year":"2018"},{"key":"ref46","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref48","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc ICML"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/9781119994138"},{"key":"ref41","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref44","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Int Conf Machine Learning"},{"key":"ref43","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/9757050\/09354210.pdf?arnumber=9354210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T21:46:51Z","timestamp":1653947211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9354210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":55,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2021.3050960","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5]]}}}